© 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. 7274
    Prev
    Next
    INDEX
    Explanations

    terms related to technology or physical features of objects, particularly at the front or front-facing

    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
    1339
    +0.13
    0.5%
    897
    +0.13
    0.5%
    489
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1339
    +0.13
    0.02
    489
    +0.13
    0.02
    757
    +0.12
    0.03
    Negative Logits
     apprehen
    -0.98
     emphat
    -0.93
     Docteur
    -0.92
     accla
    -0.92
     shenan
    -0.90
     maneu
    -0.90
     gaily
    -0.89
     depic
    -0.87
     volunte
    -0.86
     disreg
    -0.86
    POSITIVE LOGITS
    front
    1.27
     front
    1.26
    Front
    1.21
     Front
    1.18
     FRONT
    1.11
    FRONT
    1.09
     fronts
    0.99
    fron
    0.94
    Fron
    0.81
     fron
    0.78
    Activations Density 0.062%

    No Known Activations