© 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 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. 14210
    Prev
    Next
    INDEX
    Explanations

    city names and abbreviations

    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
    227
    +0.12
    0.3%
    964
    +0.09
    0.3%
    2034
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    648
    +0.12
    0.05
    512
    +0.09
    0.06
    167
    +0.09
    0.05
    Negative Logits
     saites
    -0.79
     Walkover
    -0.79
     gynhyrchwyd
    -0.78
    ffilm
    -0.73
    Todavía
    -0.73
     Février
    -0.72
     Mérimée
    -0.72
     Gennaio
    -0.71
     maig
    -0.71
    loài
    -0.70
    POSITIVE LOGITS
     USA
    0.71
     ineffec
    0.65
    ,
    0.61
    .
    0.60
     impra
    0.60
     (
    0.59
     maneu
    0.59
     Railroads
    0.58
     apprehen
    0.57
     horrend
    0.57
    Activations Density 0.129%

    No Known Activations