Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 1073
    Prev
    Next
    INDEX
    Explanations

    names and references to religious institutions and figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1343
    +0.41
    1.6%
    184
    +0.19
    0.7%
    1177
    +0.16
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.41
    0.08
    1177
    +0.19
    0.02
    16
    +0.16
    0.05
    Negative Logits
    <bos>
    -1.65
    #
    -0.81
    ,
    -0.74
     gänzlich
    -0.74
     einheit
    -0.72
     bedingt
    -0.71
     betreffenden
    -0.71
     but
    -0.71
     instead
    -0.71
     notwendi
    -0.70
    POSITIVE LOGITS
     kram
    1.91
     makro
    1.87
     Traité
    1.86
     karton
    1.85
     alkoh
    1.83
     Kategor
    1.83
     Strukt
    1.78
     elek
    1.71
     keramik
    1.71
     meis
    1.70
    Activations Density 0.165%

    No Known Activations