© 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. 3680
    Prev
    Next
    INDEX
    Explanations

    information related to historical figures and events

    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
    764
    +0.10
    0.3%
    549
    +0.10
    0.3%
    74
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    549
    +0.10
    0.06
    74
    +0.10
    0.04
    972
    +0.09
    0.03
    Negative Logits
     anhyd
    -0.55
    ">...
    -0.51
    ">“
    -0.50
     zumal
    -0.49
     limestones
    -0.48
     laad
    -0.48
     bordes
    -0.47
    <?
    -0.47
    ecuted
    -0.46
     cliquant
    -0.45
    POSITIVE LOGITS
     activism
    0.71
     nobly
    0.67
     unspeak
    0.66
     implor
    0.66
     Pfal
    0.65
     indescri
    0.65
     Majest
    0.64
     Abbé
    0.64
     activist
    0.63
     maneu
    0.62
    Activations Density 0.785%

    No Known Activations