© 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. 13711
    Prev
    Next
    INDEX
    Explanations

    explanations and descriptions related to technical concepts and inventions

    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
    674
    +0.15
    0.4%
    872
    +0.11
    0.3%
    46
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1801
    +0.15
    0.03
    46
    +0.11
    0.04
    62
    +0.08
    0.04
    Negative Logits
     keramik
    -0.71
     kooper
    -0.71
     kasa
    -0.71
     kte
    -0.69
     kosme
    -0.68
    <^
    -0.67
     „,
    -0.67
     elek
    -0.66
     maksi
    -0.66
     fré
    -0.66
    POSITIVE LOGITS
    <bos>
    0.69
     considering
    0.63
     compared
    0.60
     retrospect
    0.59
     hindsight
    0.58
    considering
    0.57
     viewed
    0.53
     zumal
    0.53
    ">/
    0.51
     vestiti
    0.51
    Activations Density 0.343%

    No Known Activations