© 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. 14199
    Prev
    Next
    INDEX
    Explanations

    details related to a specific organization and its 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
    198
    +0.18
    0.5%
    1919
    +0.12
    0.3%
    222
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.18
    0.07
    198
    +0.12
    0.07
    222
    +0.10
    0.06
    Negative Logits
     orizz
    -1.01
     sopr
    -1.01
     centrif
    -0.98
     Simult
    -0.98
     silikon
    -0.98
     olx
    -0.96
     simplif
    -0.96
     clô
    -0.96
     peculi
    -0.96
     pleins
    -0.95
    POSITIVE LOGITS
     themselves
    0.85
     either
    0.71
     are
    0.62
     have
    0.61
     want
    0.61
     their
    0.60
    either
    0.60
    themselves
    0.60
     who
    0.59
     którzy
    0.59
    Activations Density 0.479%

    No Known Activations