© 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. 14612
    Prev
    Next
    INDEX
    Explanations

    phrases related to locations or addresses

    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
    1842
    +0.20
    0.6%
    1978
    +0.17
    0.5%
    184
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.20
    0.04
    1842
    +0.17
    0.06
    845
    +0.14
    0.04
    Negative Logits
     sappi
    -1.15
     vogli
    -1.07
     comprendere
    -0.99
     trovar
    -0.95
     servire
    -0.92
     pertanto
    -0.91
     dicono
    -0.91
     rispond
    -0.88
     bangkok
    -0.88
     credere
    -0.88
    POSITIVE LOGITS
     [
    0.68
     stuff
    0.64
     really
    0.62
     cetera
    0.62
     ourselves
    0.60
     myself
    0.59
     whatnot
    0.57
     maybe
    0.56
    ,"
    0.54
     pretty
    0.53
    Activations Density 0.783%

    No Known Activations