© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14525
    Prev
    Next
    INDEX
    Explanations

    database query results containing rows and columns of data

    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
    +0.16
    0.6%
    82
    +0.16
    0.6%
    1103
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1103
    +0.16
    0.03
    82
    +0.16
    0.02
    1343
    +0.15
    0.02
    Negative Logits
     ujedno
    -0.77
     brugt
    -0.66
     tyn
    -0.56
     maske
    -0.55
     katastro
    -0.55
     zdrav
    -0.55
     fået
    -0.54
     Ży
    -0.53
    Externé
    -0.53
     ogran
    -0.53
    POSITIVE LOGITS
     |
    0.74
    ("|
    0.65
    .|
    0.65
    ('|
    0.64
     $|
    0.62
    }|
    0.60
     gmbh
    0.60
     TDA
    0.60
    ]|
    0.60
     matel
    0.60
    Activations Density 0.037%

    No Known Activations