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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 16096
    Prev
    Next
    INDEX
    Explanations

    words related to scaling processes and techniques

    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
    1505
    +0.12
    0.4%
    1276
    +0.11
    0.4%
    1581
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1505
    +0.12
    0.03
    1276
    +0.11
    0.03
    1331
    +0.11
    0.03
    Negative Logits
    FetchType
    -0.52
    poir
    -0.48
     Nunn
    -0.44
     Jovi
    -0.44
     Mit
    -0.41
     Baker
    -0.41
    aibo
    -0.41
     Bob
    -0.40
     Kut
    -0.40
    pagnole
    -0.40
    POSITIVE LOGITS
     scale
    1.29
     scales
    1.22
     Scale
    1.21
     SCALE
    1.21
    scale
    1.19
     Scales
    1.16
    Scale
    1.16
    Scales
    1.10
    scales
    1.06
     scaled
    1.06
    Activations Density 0.102%

    No Known Activations