© 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. 2031
    Prev
    Next
    INDEX
    Explanations

    timestamps

    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
    1343
    +0.13
    0.4%
    1616
    +0.09
    0.3%
    655
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1429
    +0.13
    0.05
    1788
    +0.09
    0.04
    265
    +0.08
    0.04
    Negative Logits
    Ahoj
    -0.60
    Może
    -0.57
    Merhaba
    -0.56
     pymysql
    -0.56
    Cześć
    -0.55
    Wię
    -0.54
    Folgende
    -0.53
    Genau
    -0.52
    Dazu
    -0.52
    Forked
    -0.52
    POSITIVE LOGITS
     karton
    0.53
    pm
    0.53
     siena
    0.52
     kommunik
    0.49
     cittad
    0.49
     labd
    0.49
     konkre
    0.49
     akade
    0.49
    PM
    0.49
     koordin
    0.49
    Activations Density 0.076%

    No Known Activations