© 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. 1970
    Prev
    Next
    INDEX
    Explanations

    dependency and reliance on various factors and entities

    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
    752
    +0.14
    0.4%
    1056
    +0.10
    0.3%
    1708
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    95
    +0.14
    0.02
    1708
    +0.10
    0.02
    1464
    +0.10
    0.02
    Negative Logits
    <bos>
    -0.56
     geze
    -0.44
     Böyle
    -0.44
    irmish
    -0.43
     beneficiario
    -0.43
    DisplayMetrics
    -0.42
    kově
    -0.42
    matic
    -0.41
    ראלי
    -0.41
    viewDidLoad
    -0.40
    POSITIVE LOGITS
     quitt
    0.69
     écout
    0.68
     triomphe
    0.68
     coffret
    0.66
     plong
    0.64
     eyel
    0.63
     délib
    0.63
     récon
    0.63
     espé
    0.61
     dégust
    0.61
    Activations Density 0.114%

    No Known Activations