© 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. 14424
    Prev
    Next
    INDEX
    Explanations

    publication citations

    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
    2034
    +0.18
    0.6%
    674
    +0.16
    0.5%
    1323
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1323
    +0.18
    0.03
    1966
    +0.16
    0.02
    497
    +0.14
    0.03
    Negative Logits
    Răsp
    -0.60
    Lebih
    -0.59
    Př
    -0.58
    Pře
    -0.58
    Şi
    -0.58
    Cordialement
    -0.57
    Wię
    -0.56
    Selama
    -0.55
    Kelebihan
    -0.55
    Kdo
    -0.55
    POSITIVE LOGITS
     [''],
    0.75
    <bos>
    0.73
     '*')
    0.73
     gmbh
    0.70
     '.')
    0.68
     jacques
    0.68
     veau
    0.66
     "/")
    0.66
    Билгалдахарш
    0.65
     ""))
    0.64
    Activations Density 0.099%

    No Known Activations