© 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. 13724
    Prev
    Next
    INDEX
    Explanations

    pronouns referring to possession or affiliation

    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
    1385
    +0.14
    0.4%
    1741
    +0.12
    0.4%
    1937
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    131
    +0.14
    0.06
    1937
    +0.12
    0.07
    332
    +0.11
    0.06
    Negative Logits
     gaily
    -1.11
     inconce
    -1.10
     excru
    -1.10
     disagre
    -1.09
     impra
    -1.06
     apprehen
    -1.04
     indescri
    -1.04
     fortn
    -1.04
     reluct
    -1.00
     depic
    -0.99
    POSITIVE LOGITS
     reputa
    0.70
     own
    0.69
     entire
    0.64
     eyes
    0.58
    OGND
    0.58
    ὁ
    0.58
     مرئيه
    0.56
     parents
    0.55
     Darum
    0.54
    astéro
    0.54
    Activations Density 0.322%

    No Known Activations