© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 3944
    Prev
    Next
    INDEX
    Explanations

    information related to technological advancements and innovations, particularly in the fields of biotechnology and electronics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    876
    +0.19
    0.6%
    752
    +0.12
    0.3%
    1385
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    876
    +0.19
    -0.02
    394
    +0.12
    0.04
    942
    +0.10
    0.04
    Negative Logits
     pamph
    -1.44
     accla
    -1.27
     Keny
    -1.26
     shenan
    -1.23
     reluct
    -1.18
     Khart
    -1.14
     apprehen
    -1.13
     maneu
    -1.12
     philanth
    -1.12
     Immig
    -1.10
    POSITIVE LOGITS
     getItemId
    0.61
    zonder
    0.56
     chemic
    0.53
    ISPR
    0.52
    lyser
    0.51
    focusable
    0.51
    ilitatea
    0.51
     PATENT
    0.51
    fontName
    0.50
    wunsch
    0.50
    Activations Density 0.500%

    No Known Activations