© 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. 14164
    Prev
    Next
    INDEX
    Explanations

    ongoing projects or activities

    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
    1363
    +0.12
    0.4%
    411
    +0.11
    0.3%
    204
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.12
    0.06
    204
    +0.11
    0.04
    284
    +0.10
    0.06
    Negative Logits
     préc
    -0.89
     effe
    -0.86
     encomp
    -0.86
     alre
    -0.85
     Manufact
    -0.85
     guarante
    -0.83
     resear
    -0.82
     Intere
    -0.82
     réuss
    -0.82
     opport
    -0.80
    POSITIVE LOGITS
     חיצוניים
    0.79
     antwortete
    0.75
    躇
    0.75
     glaubte
    0.72
    liminaries
    0.71
     hornblende
    0.70
    gruntled
    0.69
     [],
    
    0.68
     anhydride
    0.67
     gneiss
    0.66
    Activations Density 0.479%

    No Known Activations