© 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. 927
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions involving giving or transferring something to someone

    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
    1895
    +0.12
    0.4%
    1044
    +0.10
    0.3%
    1464
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1895
    +0.12
    0.02
    1142
    +0.10
    0.02
    569
    +0.10
    0.02
    Negative Logits
    ajur
    -0.47
     Profile
    -0.45
    Profile
    -0.45
    profile
    -0.44
    badah
    -0.42
    PROFILE
    -0.42
     bunda
    -0.41
    Ҫ
    -0.41
    bele
    -0.40
    ABN
    -0.40
    POSITIVE LOGITS
     handed
    1.10
     handing
    1.01
    handed
    0.84
     hand
    0.75
     handover
    0.73
     Hand
    0.69
    Hand
    0.69
     HAND
    0.67
    hand
    0.67
     hands
    0.64
    Activations Density 0.075%

    No Known Activations