© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 13027
    Prev
    Next
    INDEX
    Explanations

    information about archaeological discoveries and early societies, as well as details about scientific studies and research

    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
    1871
    +0.12
    0.4%
    872
    +0.12
    0.4%
    198
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.12
    0.06
    185
    +0.12
    0.04
    1441
    +0.10
    0.04
    Negative Logits
    hasMoreElements
    -0.68
     psychiat
    -0.64
     gesta
    -0.63
    ]")]
    -0.60
    rungsseite
    -0.60
     utop
    -0.58
     solidar
    -0.57
     katal
    -0.56
     Gratis
    -0.55
    twimg
    -0.54
    POSITIVE LOGITS
     unwarran
    1.18
     shewn
    1.10
     unlaw
    1.04
     ftill
    1.00
     Whence
    0.99
     disagre
    0.98
     reluct
    0.94
     tolerably
    0.93
     increa
    0.92
     liberality
    0.92
    Activations Density 0.603%

    No Known Activations