© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 7479
    Prev
    Next
    INDEX
    Explanations

    references to specific locations and historical events

    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
    964
    +0.16
    0.5%
    1177
    +0.13
    0.4%
    1343
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1540
    +0.16
    0.02
    1247
    +0.13
    0.05
    964
    +0.11
    0.03
    Negative Logits
    <bos>
    -0.60
     Schwier
    -0.59
     ThemeData
    -0.59
     Baillargeon
    -0.58
    styleUrls
    -0.56
    ppelin
    -0.56
     Fahr
    -0.55
    declarations
    -0.55
    ांकि
    -0.54
    HttpFoundation
    -0.54
    POSITIVE LOGITS
     reluct
    1.98
     disagre
    1.98
     Juf
    1.95
     philanth
    1.93
     pamph
    1.92
     unspeak
    1.90
     apprehen
    1.90
     volunte
    1.90
     depic
    1.90
     shenan
    1.89
    Activations Density 0.694%

    No Known Activations