© 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. 14636
    Prev
    Next
    INDEX
    Explanations

    information related to technology collaborations, partnerships, and projects

    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
    1120
    +0.15
    0.5%
    678
    +0.10
    0.3%
    227
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1445
    +0.15
    0.09
    400
    +0.10
    0.06
    388
    +0.10
    0.05
    Negative Logits
     îna
    -0.68
     dă
    -0.66
     răm
    -0.62
     uș
    -0.60
     destul
    -0.59
     împre
    -0.59
    Și
    -0.58
     arată
    -0.58
    municipi
    -0.58
     ușor
    -0.58
    POSITIVE LOGITS
     Expt
    0.69
     Excited
    0.65
     Pamph
    0.63
     Exciting
    0.62
     Inhabitants
    0.61
     Abstr
    0.59
     Announcements
    0.59
     unwarran
    0.59
     Aims
    0.59
     Speeches
    0.59
    Activations Density 0.932%

    No Known Activations